Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to self-reflection and personal accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows general words, like school, else, much

    np_acts-logits-general · gemini-2.0-flash

    terms of address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ？）
    -0.50
    ?」
    -0.47
     samt
    -0.47
    =");
    -0.47
    =*/
    -0.46
     UIKit
    -0.46
     absl
    -0.46
    )」
    -0.46
    makeText
    -0.46
    casila
    -0.45
    POSITIVE LOGITS
     dear
    1.47
     guys
    1.45
     sir
    1.45
     mate
    1.41
     buddy
    1.40
     dude
    1.33
     fellas
    1.28
     gentlemen
    1.26
     bro
    1.24
     folks
    1.23
    Act Density 0.509%

    No Known Activations